qi d Z ddlmZmZmZmZmZmZmZ ddl m
Z
ddl m Z ddl
mZ ddlmZ ej" e Zdd d
Zd ZdZd Zd
ZdZdZ G d de ZdgZ y)z%Tokenization classes for XLNet model. )
AddedTokenRegex Tokenizerdecoders normalizerspre_tokenizers
processors)Unigram )_get_prepend_scheme)TokenizersBackend)loggingz spiece.modelztokenizer.json)
vocab_filetokenizer_file ▁ c p e Zd ZdZeZdZeZ dde e
e e e f z dz de
f fd
Z xZS )XLNetTokenizera
Construct a XLNet tokenizer (backed by HuggingFace's *tokenizers* library). Based on
[Unigram](https://huggingface.co/docs/tokenizers/python/latest/components.html?highlight=unigram#models).
This tokenizer inherits from [`TokenizersBackend`] which contains most of the main methods. Users should
refer to this superclass for more information regarding those methods.
Args:
vocab (`list of tuples`, *optional*):
List of (token, score) tuples for Unigram model. If not provided, an empty list is used.
unk_id (`int`, *optional*, defaults to 0):
The ID of the unknown token in the vocabulary.
do_lower_case (`bool`, *optional*, defaults to `False`):
Whether to lowercase the input when tokenizing.
remove_space (`bool`, *optional*, defaults to `True`):
Whether to strip the text when tokenizing (removing excess spaces before and after the string).
keep_accents (`bool`, *optional*, defaults to `False`):
Whether to keep accents when tokenizing.
bos_token (`str`, *optional*, defaults to `""`):
The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.
When building a sequence using special tokens, this is not the token that is used for the beginning of
sequence. The token used is the `cls_token`.
eos_token (`str`, *optional*, defaults to `""`):
The end of sequence token.
When building a sequence using special tokens, this is not the token that is used for the end of sequence.
The token used is the `sep_token`.
unk_token (`str`, *optional*, defaults to `""`):
The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
token instead.
sep_token (`str`, *optional*, defaults to `""`):
The separator token, which is used when building a sequence from multiple sequences, e.g. two sequences for
sequence classification or for a text and a question for question answering. It is also used as the last
token of a sequence built with special tokens.
pad_token (`str`, *optional*, defaults to `""`):
The token used for padding, for example when batching sequences of different lengths.
cls_token (`str`, *optional*, defaults to `""`):
The classifier token which is used when doing sequence classification (classification of the whole sequence
instead of per-token classification). It is the first token of the sequence when built with special tokens.
mask_token (`str`, *optional*, defaults to `""`):
The token used for masking values. This is the token used when training this model with masked language
modeling. This is the token which the model will try to predict.
additional_special_tokens (`list[str]`, *optional*, defaults to `["", ""]`):
Additional special tokens used by the tokenizer.
leftNvocabunk_idc |
ddg}
||| _ nt | dfg| _ t t | j |d | _ t j dd t j dd g}|j t j |j t j |r#|j t j |j t j t d d
t j | | j _
d }t || }t j t j t j" d |
g | j _ t' j" d |
| j _ d| _ || _ || _ || _ t3 | t rt5 | d d n| } t7 | p d|||||||| |
| | |
d | t; j< dt | j> dt | j@ ddt | j> dt | j> dt | j@ dt | j> | jB ft | j@ | jD fg | j _# y )Nzzg F)r
byte_fallbackz``"z''z {2,} Tr ) replacementprepend_schemer )lstriprstrip) r
do_lower_case remove_space keep_accents bos_token eos_token unk_token sep_token pad_token cls_token
mask_tokenadditional_special_tokensz$A:0 z:0 z:2z:0 $B:1 z:1 )singlepairspecial_tokens )$_vocabstrr r
_tokenizerr ReplaceappendNFKD StripAccents Lowercaser Sequence
normalizerr r WhitespaceSplit Metaspace
pre_tokenizerr decoder_pad_token_type_idr" r# r$
isinstancer super__init__r TemplateProcessingr( r* sep_token_id cls_token_idpost_processor)selfr r r" r# r$ r% r& r' r( r) r* r+ r, kwargslist_normalizersadd_prefix_spacer __class__s ^/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/xlnet/tokenization_xlnet.pyrB zXLNetTokenizer.__init__d s " % ,)0'(: % DK NC01DK# #
c * c *
0 0 23 8 8 :; # #K$9$9$; < 3 3E'NC HI%0%9%9:J%K" ,-=tD(6(?(? ..0 ((U>Z
)
% #+"4"4We"f "# * ( (JTU_adJeZ
4Fku
'%% !&?
*4)F)F3t~~./s3t~~3F2GrJT^^,-Xc$..6I5J#cRVR`R`NaMbbdeT^^$d&7&78T^^$d&7&78 *
& )
Nr FTFzzzzzzzN)__name__
__module__ __qualname____doc__VOCAB_FILES_NAMESvocab_files_names padding_sider
modelr2 listtuplefloatintrB
__classcell__)rK s @rL r r & s| 7r *L E 7;"& T
T%U
+,,t3T
T
T
rM r N) rQ
tokenizersr r r r r r r tokenizers.modelsr
tokenization_utils_baser tokenization_utils_tokenizersr
utilsr
get_loggerrN loggerrR SPIECE_UNDERLINESEG_ID_ASEG_ID_B
SEG_ID_CLS
SEG_ID_SEP
SEG_ID_PADr __all__r0 rM rL ri sz , f f f % : >
H %#1EUV
R
& R
j
rM